Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2669 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4891. Min Range: -1.4891

Max Act: 1.4891. Min Act: -0.0000

Data Index: 178330 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 1.4891. Min Range: -1.4891

Max Act: 1.3892. Min Act: -0.0000

Data Index: 903585 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 1.4891. Min Range: -1.4891

Max Act: 1.3413. Min Act: -0.0000

Data Index: 559226 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 1.4891. Min Range: -1.4891

Max Act: 1.4072. Min Act: -0.0000

Data Index: 50641 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 1.4891. Min Range: -1.4891

Max Act: 1.2131. Min Act: -0.0000

Data Index: 1061988 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 1.4891. Min Range: -1.4891

Max Act: 1.2607. Min Act: -0.0000

Data Index: 11167 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 1.4891. Min Range: -1.4891

Max Act: 1.3362. Min Act: -0.0000

Data Index: 464343 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 1.4891. Min Range: -1.4891

Max Act: 1.2910. Min Act: -0.0000

Data Index: 198706 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 1.4891. Min Range: -1.4891

Max Act: 1.1805. Min Act: -0.0000

Data Index: 936253 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 1.4891. Min Range: -1.4891

Max Act: 1.2123. Min Act: -0.0000

Data Index: 865480 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 1.4891. Min Range: -1.4891

Max Act: 1.1327. Min Act: -0.0000

Data Index: 212836 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 1.4891. Min Range: -1.4891

Max Act: 1.1776. Min Act: -0.0000

Data Index: 11111 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 1.4891. Min Range: -1.4891

Max Act: 1.1348. Min Act: -0.0000

Data Index: 124709 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 1.4891. Min Range: -1.4891

Max Act: 1.0874. Min Act: -0.0000

Data Index: 788335 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 1.4891. Min Range: -1.4891

Max Act: 1.1193. Min Act: -0.0000

Data Index: 679170 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 1.4891. Min Range: -1.4891

Max Act: 1.1165. Min Act: -0.0000

Data Index: 489433 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 1.4891. Min Range: -1.4891

Max Act: 1.1241. Min Act: -0.0000

Data Index: 1106765 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 1.4891. Min Range: -1.4891

Max Act: 1.0555. Min Act: -0.0000

Data Index: 1278683 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 1.4891. Min Range: -1.4891

Max Act: 1.1120. Min Act: -0.0000

Data Index: 733865 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 1.4891. Min Range: -1.4891

Max Act: 1.0832. Min Act: -0.0000

Data Index: 925693 (C4 (Web Text))

Max Activating Token Index: 857